Development of neural networks module for fault identification in asynchronous machine using various types of reference signals

In this article, the device of automatic diagnostic of asynchronous motor is discussed. This diagnostic system is based on artificial neural network (ANN), in order to find the different defects by classification. The machine health identification process is mainly based on recognition and comparison of real-time captured standard signature as stator current, rotation speed of machine. The features extraction of the instantaneous signals will then input to an artificial neural networks (ANN) for recognition and identification. The output of the neural network was trained to generate a healthy index that indicates the machine health condition. In this work, the entries used in the neural network were the various types of signals: the instantaneous values and the effective values (root mean square) of the machine parameters.